Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4526 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.8499. Min Act: -0.1700
Data Index: 7492015 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.8499. Min Act: -0.1700
Data Index: 482744 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.7249. Min Act: -0.1700
Data Index: 7743989 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.6311. Min Act: -0.1700
Data Index: 860671 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5999. Min Act: -0.1700
Data Index: 6800072 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5686. Min Act: -0.1700
Data Index: 3639295 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5374. Min Act: -0.1700
Data Index: 3976259 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.5061. Min Act: -0.1700
Data Index: 8171295 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4749. Min Act: -0.1700
Data Index: 4546013 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4436. Min Act: -0.1700
Data Index: 4231528 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4124. Min Act: -0.1700
Data Index: 3175892 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4124. Min Act: -0.1700
Data Index: 137330 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.4124. Min Act: -0.1700
Data Index: 161331 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 3626464 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 1809665 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3811. Min Act: -0.1700
Data Index: 7385356 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3186. Min Act: -0.1700
Data Index: 3309692 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.3186. Min Act: -0.1700
Data Index: 3460721 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.2561. Min Act: -0.1700
Data Index: 7749167 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8499. Min Range: -6.8499
Max Act: 6.2561. Min Act: -0.1700
Data Index: 5853735 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19